Paperlane

no. 14 · Friday 13 November 2026

Rateless Coding for Efficient Model Broadcast in Federated Learning

Zijun Qin, Zuolin Jin, Jingxuan Huang, Ming Xiao and Xianhao Chen

math.IT

Abstract

Model broadcast in federated learning (FL) with wireless channels faces significant challenges due to large model sizes and heterogeneous, unreliable channel conditions. While rateless coding has been widely adopted in modern broadcast communications to handle channel heterogeneity, its potential for model broadcast in FL remains largely unexplored. To fill this gap, we propose a joint source-channel coding scheme based on rateless coding to improve the robustness and efficiency of downlink model broadcast in FL. Specifically, we establish a rigorous convergence analysis of FL to inform the rateless code and quantization design under noisy downlink channel conditions. Moreover, by observing that the iterative process of FL naturally provides prior information about client updates, we leverage client-side local models as conditional prior information to aid the decoding process, thereby reducing transmission costs. Extensive simulations demonstrate that our rateless coding scheme significantly enhances downlink model broadcast efficiency in FL, while retaining comparable training accuracies for both homogeneous and heterogeneous data distributions.

fields
Information Theory
pdf ↗ page arXiv:2611.15499 ↗